Abstract / Summary
Abstract Attention Deficit Hyperactivity Disorder (ADHD) is a prevalent neurodevelopmental disorder that is frequently associated with sleep disturbances. Early identification of ADHD using objective sleep-related parameters has the potential to improve diagnosis and facilitate timely intervention. This study proposes a machine learning-based framework for the classification of ADHD using publicly available sleep-related physiological and clinical features. After preprocessing and feature engineering, a Random Forest classifier was trained and optimized using GridSearchCV with stratified cross-validation. Model performance was evaluated using accuracy, precision, recall, F1-score, balanced accuracy, Matthews Correlation Coefficient (MCC), and the Area Under the Receiver Operating Characteristic Curve (ROC-AUC). The proposed approach achieved promising classification performance, demonstrating the feasibility of using sleep-derived features for ADHD prediction. These findings highlight the potential of machine learning as a supportive tool for the early screening of ADHD.